Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical values or amounts depicted in various formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Allaah
    -0.16
    nces
    -0.16
     ye
    -0.16
     Horus
    -0.16
    govtrack
    -0.15
    [/
    -0.15
     sts
    -0.15
     Meow
    -0.15
    pas
    -0.15
    aws
    -0.14
    POSITIVE LOGITS
    idth
    0.16
    querque
    0.16
    ł
    0.15
     unpop
    0.15
    userc
    0.15
    zens
    0.14
    ãĥ¼ãĥ³
    0.14
    Multi
    0.14
     Newly
    0.13
     inflammation
    0.13
    Act Density 10.258%

    No Known Activations